Update app.py

app.py

@@ -49,27 +49,33 @@ def perform_blast_analysis(sequence):
             
             if blast_record.alignments:
                 alignment = blast_record.alignments[0]  # Get the top hit
+                hsp = alignment.hsps[0]  # Get the first (best) HSP
                 
-                organism = alignment.title.split('OS=')[-1].split('OX=')[0].strip()
-                organism = organism.split()[0] if len(organism.split()) > 1 else organism
+                # Extract protein name and organism
+                title_parts = alignment.title.split('|')
+                protein_name = title_parts[-1].strip()
+                organism = title_parts[-2].split('OS=')[-1].split('OX=')[0].strip()
                 
-                st.write(f"**Estimated Organism:** This protein sequence shares similarities with proteins found in {organism}.")
+                # Calculate identity percentage
+                identity_percentage = (hsp.identities / alignment.length) * 100
                 
+                st.write(f"**Top Match:** {protein_name}")
+                st.write(f"**Organism:** {organism}")
+                st.write(f"**Sequence Identity:** {identity_percentage:.2f}%")
+                st.write(f"**E-value:** {hsp.expect:.2e}")
+                
+                # Fetch protein function (if available)
                 if hasattr(alignment, 'description') and alignment.description:
-                    function = alignment.description.split('[')[0].strip()
-                    st.write(f"**Potential Function:** This protein might be involved in {function.lower()}.")
-                else:
-                    st.write("**Potential Function:** Unable to determine a specific function for this protein sequence.")
+                    st.write(f"**Potential Function:** {alignment.description}")
                 
-                st.markdown("[Learn more about protein functions](https://www.nature.com/scitable/topicpage/protein-function-14123348/)")
+                # Link to BLAST results
+                blast_link = f"https://blast.ncbi.nlm.nih.gov/Blast.cgi?PROGRAM=blastp&PAGE_TYPE=BlastSearch&LINK_LOC=blasthome"
+                st.markdown(f"[View full BLAST results (may require re-running the search)]({blast_link})")
             else:
-                st.write("No close matches found. This might be a unique protein sequence!")
+                st.write("No significant matches found. This might be a unique protein sequence!")
         except Exception as e:
-            st.error("An error occurred during protein analysis. Please try again later.")
-
-import streamlit as st
-
-# ... (keep all previous imports and functions)
+            st.error(f"An error occurred during protein analysis: {str(e)}")
+            st.write("Please try again later or contact support if the issue persists.")
 
 def update(sequence, word1, word2, word3, sequence_length):
     headers = {
@@ -90,33 +96,15 @@ def update(sequence, word1, word2, word3, sequence_length):
         struct = bsio.load_structure('predicted.pdb', extra_fields=["b_factor"])
         b_value = round(struct.b_factor.mean(), 2)
         
-        st.subheader(f'Predicted protein structure using seed: {word1}, {word2}, and {word3} + length {sequence_length}')
-        render_mol(pdb_string)
-        
-        st.subheader('plDDT Score')
-        st.write('plDDT is a per-residue estimate of the confidence in prediction on a scale from 0-100%.')
-        st.info(f'Average plDDT: {int(b_value * 100)}%')
+        st.session_state.structure_info = {
+            'pdb_string': pdb_string,
+            'b_value': b_value,
+            'word1': word1,
+            'word2': word2,
+            'word3': word3,
+            'sequence_length': sequence_length
+        }
         
-        st.download_button(
-            label="Download PDB",
-            data=pdb_string,
-            file_name='predicted.pdb',
-            mime='text/plain',
-        )
-
-        st.markdown("""
-        ## What to do next:
-        If you find interesting results from the sequence folding, you can explore further:
-        1. Learn more about protein structures and sequences.
-        2. Visit the [Protein Data Bank (PDB)](https://www.rcsb.org/) for known protein structures.
-        3. Compare your folded structure with known functional proteins by downloading your results.
-        4. Read about similar proteins to gain insights into potential functions.
-        5. Click the "Analyze Protein" button below to get more information about your generated protein.
-
-        **Remember, this folding is based on randomly generated sequences. Interpret the results with caution.
-        Enjoy exploring the world of protein sequences! Share your high-confidence protein images with us on X [*@WandsAI*](https://x.com/wandsai)!
-        """)
-
         st.session_state.show_analyze_button = True
 
     except requests.exceptions.RequestException as e:
@@ -128,6 +116,8 @@ if 'sequence' not in st.session_state:
     st.session_state.sequence = None
 if 'show_analyze_button' not in st.session_state:
     st.session_state.show_analyze_button = False
+if 'structure_info' not in st.session_state:
+    st.session_state.structure_info = None
 
 st.title("Word-Seeded Protein Sequence Generator and Structure Predictor")
 
@@ -149,6 +139,36 @@ if st.sidebar.button('Generate and Predict'):
     else:
         st.sidebar.warning("Please enter all three words to generate a sequence.")
 
+# Display structure information if available
+if st.session_state.structure_info:
+    info = st.session_state.structure_info
+    st.subheader(f'Predicted protein structure using seed: {info["word1"]}, {info["word2"]}, and {info["word3"]} + length {info["sequence_length"]}')
+    render_mol(info['pdb_string'])
+    
+    st.subheader('plDDT Score')
+    st.write('plDDT is a per-residue estimate of the confidence in prediction on a scale from 0-100%.')
+    st.info(f'Average plDDT: {int(info["b_value"] * 100)}%')
+    
+    st.download_button(
+        label="Download PDB",
+        data=info['pdb_string'],
+        file_name='predicted.pdb',
+        mime='text/plain',
+    )
+
+    st.markdown("""
+    ## What to do next:
+    If you find interesting results from the sequence folding, you can explore further:
+    1. Learn more about protein structures and sequences.
+    2. Visit the [Protein Data Bank (PDB)](https://www.rcsb.org/) for known protein structures.
+    3. Compare your folded structure with known functional proteins by downloading your results.
+    4. Read about similar proteins to gain insights into potential functions.
+    5. Click the "Analyze Protein" button below to get more information about your generated protein.
+
+    **Remember, this folding is based on randomly generated sequences. Interpret the results with caution.
+    Enjoy exploring the world of protein sequences! Share your high-confidence protein images with us on X [*@WandsAI*](https://x.com/wandsai)!
+    """)
+
 # Show the Analyze Protein button if a sequence has been generated
 if st.session_state.show_analyze_button:
     if st.button('Analyze Protein'):